COVID-19 PANDEMİ SÜRECİNDE TWİTTER YORUMLARI İLE ALTCOIN KRİPTO PARA PİYASASI ARASINDAKİ NEDENSELLİĞİN DUYGU ANALİZİ İLE İNCELENMESİ: RİPPLE ÖRNEĞİ

Year 2021, Volume: 19 Issue: 4, 362 - 381, 31.12.2021

Utku Erdinç Nurbanu Bursa

https://doi.org/10.11611/yead.991718

Cited By: 1

Abstract

Covid-19 pandemisinin dünya genelinde sağlık, eğitim gibi alanlarda olduğu gibi ekonomi alanındaki etkisi de oldukça büyüktür. Salgınla mücadele kapsamında uygulanan kapanma süreçleri ve çalışma saatlerindeki değişiklikler, bireylerin ekonomik durumlarında bozulmalara yol açmış ve bunun bir sonucu olarak, sosyal medyanın da etkisiyle çeşitli yatırım araçlarına gösterilen ilgi artmıştır. Bu yatırım araçlarından birisi de, kripto paralar olmuştur. Çalışmada, Twitter kullanıcılarının Ripple hakkında paylaştıkları Türkçe tweetler ile Ripple’ın gün sonu fiyatı arasındaki nedensellik, Covid-19 pandemi sürecinde duygu analizi ve nedensellik testiyle incelenmiştir. Duygu analizi sonucunda elde edilen duygu skorları ile aynı tarihlerdeki Ripple’a ait gün sonu kapanış fiyatları arasında pozitif yönlü %21’lik bir korelasyon elde edilmiştir. Sonrasında, ilgilenilen değişkenlerin aynı düzeylerde durağan olmamalarından dolayı Toda-Yamamoto nedensellik testi uygulanmış ve tek yönlü bir nedensellik bulunmuştur. Analizler sonucunda #xrp etiketi ile paylaşılan Türkçe tweetlerin, Ripple’ın fiyatları üzerinde etkisi olduğu istatistiksel olarak ortaya konmuş; ancak fiyatların Türkçe Twitter yorumlarını etkilediğine dair yeterince bir kanıt bulunamamıştır.

Keywords

Duygu Analizi, Kripto Para, Nedensellik, Twitter, Toda-Yamamoto Testi

INVESTIGATION OF THE CAUSALITY BETWEEN TWITTER COMMENTS AND ALTCOIN CRYPTOCURRENCY MARKET BY SENTIMENT ANALYSIS DURING THE COVID-19 PANDEMIC: RIPPLE EXAMPLE

Abstract

The impact of the Covid-19 pandemic on the economy, like health and education, is also quite large worldwide. The quarantines and changes in working hours implemented within the scope of the fight against the pandemic led to deterioration in the economic situation of individuals. Along with these deteriorations, the interest in various investment instruments has increased with the effect of social media. One of these investment tools is cryptocurrencies. In this context, the causality between Twitter users' Turkish tweets about Ripple and Ripple's end-of-day closing price was examined by sentiment analysis and causality test during the Covid-19 pandemic era. A positive 21% correlation was obtained between the sentiment scores obtained as a result of sentiment analysis and the end-of-day closing price of Ripple on the same dates. Afterward, because the variables were not stationary at the same levels, the Toda-Yamamoto causality test was applied and a one-way causality was found. As a result of the analysis, it was statistically revealed that Turkish tweets shared with the #xrp hashtag had an effect on Ripple's prices, however, there was not enough evidence that prices affect Turkish Twitter comments.

Keywords

Sentiment Analysis, Cryptocurrency, Causality, Twitter, Toda-Yamamoto Test

References

• Akerlof, G. ve Shiller, R., (2009), “Animal Spirits: How Human Psychology Drives the Economy and Why It Matters for Global Capitalism”, Princeton, NJ: Princeton University Press.
• Bollen, J., Mao, H. ve Zeng, X., (2011), “Twitter Mood Predicts the Stock Market”, Journal of Computational Science, 2(1): 1-8.
• Boudad, N., Faizi, R., Rachid, O. H. ve Chiheb, R., (2017), “Sentiment Analysis in Arabic: A Review of the Literature”, Ain Shams Engineering Journal, 9(4): 2479-2490.
• Bursa, N., (2019), “Visualization of Relationships Between Conventional Investment Instruments and Cryptocurrencies”, Cryptocurrencies in all Aspects, Peter Lang, Berlin.
• Ceyhan, K., Kurtulmaz, E., Sert, O. C., ve Ozyer, T., (2018), “Bitcoin Movement Prediction with Text”. 26th IEEE Signal Processing and Communications Applications Conference, 1–4.
• Coinmarketcap, (2021), https://coinmarketcap.com/. (Erişim Tarihi: 05/04/2021)
• Çarkacıoğlu, A, (2016), “Kripto-Para Bitcoin”, Sermaye Piyasası Kurulu Araştırma Dairesi Araştırma Raporu.
• Çılgın, C., (2020), “Metin Sınıflandırmada Yapay Sinir Ağları ile Bitcoin Fiyatları ve Sosyal Medyadaki Beklentilerin Analizi In Text Classification, Bitcoin Prices and Analysis of Expectations in Social Media with Artificial Neural Networks”, 4(1): 106–126.
• Dolado, J.J. ve Lütkepohl, H., (1996), “Making Wald Tests Work for Cointegrated VAR Systems”, Econometric Reviews, 15(4): 369-386.
• Dritsaki, C., (2017), “Toda-Yamamoto Causality Test between Inflation and Nominal Interest Rates: Evidence from Three Countries of Europe”, International Journal of Economics and Financial Issues, 7(6): 120.
• Hmamouche, Y., (2020), "NlinTS: An R Package for Causality Detection in Time Series”, The R Journal, 12(1): 21-31.
• Gaikwad, S.V., Chaugule, A., ve Patil, P., (2014), “Text Mining Methods and Techniques”, International Journal of Computer Applications, 85(17): 42-45.
• Gao, X., Huang, W., ve Wang, H., (2021), “Financial Twitter Sentiment on Bitcoin Return and High-Frequency Volatility”, Virtual Economics, 4(1): 7-18.
• Groß-Klußmann, A., König, S., ve Ebnera, M., (2019), “Buzzwords Build Momentum: Global Financial Twitter Sentiment and the Aggregate Stock Market”, Expert Systems with Applications, 136(1): 171-186.
• Günay, S., (2019), “Impact of Public Information Arrivals on Cryptocurrency Market: A Case of Twitter Posts on Ripple”, East Asian Economic Review, 23(2): 149-168.
• Guo, X. ve Li, J., (2019), “A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency”, Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), IEEE: 472-477.
• Gürsoy, S., (2020), “Koronavirüs Bi̇li̇ni̇rli̇ği̇ni̇n Uluslararası Ri̇sk (Volati̇li̇te) Endeksleri Üzeri̇ndeki Etki̇si̇ni̇n İncelenmesi̇, Toda-Yamamoto Nedenselli̇k Uygulaması”, Journal of Business in The Digital Age, 3(2): 84–93.
• Investing Türkiye, (2021), https://tr.investing.com/crypto/xrp/historical-data. (Erişim Tarihi: 30/04/2021).
• Kadılar, C. ve Çekim, H.Ö. (2020), “Spss ve R Uygulamalı Zaman Serileri Analizine Giriş”, Seçkin Yayıncılık.
• Kızılkaya, Y. M., (2018), “Duygu Analizi ve Sosyal Medya Alanında Uygulama”, Doktora Tezi, Uludağ Üniversitesi Sosyal Bilimler Enstitüsü, Bursa.
• Kitapcı, İ., (2018), “İktisat Sosyolojisi: İktisadi Davranışlara Sosyolojik Bir Bakış”, Uluslararası Ekonomik Araştırmalar Dergisi, 4(3): 23–41.
• Konaklı, D.N, (2020), “Birim Kök Testlerinin Makroekonomik Değişkenler Üzerine Uygulamaları”, Yüksek Lisans Tezi, Çukurova Üniversitesi Sosyal Bilimler Enstitüsü, Adana.
• Koç, Ö., (2015), “Türkiye’de Doğrudan Yabancı Yatırımlar ile İhracat ve İthalat Arasındaki Nedensellik”, Yüksek Lisans Tezi, Karadeniz Teknik Üniversitesi Sosyal Bilimler Enstitüsü, Trabzon.
• Liu, B., (2012), “Sentiment Analysis and Opinion Mining”, Toronto: Morgan & Claypool Publishers.
• Nakamoto, S., (2008), “Bitcoin: A Peer-to-Peer Electronic Cash System”, Decentralized Business Review, 21260.
• Nisar, T.M., ve Yeung, M., (2018), “Twitter as a Tool for Forecasting Stock Market Movements: A Short-window Event Study”, The Journal of Finance and Data Science, 4(2): 101-119.
• Nofer, M., ve Hinz, O., (2015), “Using Twitter to Predict the Stock Market”. Business & Information Systems Engineering, 57(4): 229-242.
• Nti, I. K., Adekoya, A.F. ve Weyori, B.A., (2020), “Predicting Stock Market Price Movement Using Sentiment Analysis: Evidence From Ghana”, Applied Computer Systems, 25(1): 33-42.
• Pagolu, V. S., Reddy, K. N., Panda, G., ve Majhi, B., (2016), “Sentiment analysis of Twitter data for predicting stock market movements”, International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), IEEE: 1345-1350.
• Philippas, D., Rjiba, H., Guesmi, K., and Goutte, S., (2019), “Media Attention and Bitcoin Prices”, Finance Research Letters, 30: 37-43.
• Polat, M., ve Akbiyik, A., (2019), “Sosyal Medya ve Yatırım Araçlarının Değeri Arasındaki İlişkinin İncelenmesi: Bitcoin Örneği”, Akademik İncelemeler Dergisi, 14(1): 443-462.
• Sağlam, F., Genç, B. ve Sever, H., (2019), "Extending a Sentiment Lexicon with Synonym-Antonym Datasets: SWNetTR++", Turkish Journal of Electrical Engineering and Computer Sciences, 27: 1806-1820.
• Seker, S.E., (2016), “Duygu Analizi (Sentimental Analysis)”, Yönetim Bilişim Sistemleri Ansiklopedi, 3(3): 21-35.
• Shanaev, S., Sharma, S., Ghimire, B. ve Shuraeva, A., (2020), “Taming the Blockchain Beast? Regulatory Implications for the Cryptocurrency Market”, Research International Business and Finance, 51(101080).
• Shen, D., Urquhart, A., ve Wang, P., (2019), “Does Twitter Predict Bitcoin?”, Economics Letters, 174: 118-122.
• Si, J., Mukherjee, A., Liu, B., Li, Q., Li, H., ve Deng, X., (2013), “Exploiting Topic Based Twitter Sentiment for Stock Prediction”, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 2: 24-29.
• Statista Research Department, (2021), “Number of cryptocurrencies worldwide from 2013 to July 2021”, statista: https://www.statista.com/statistics/863917/number-crypto-coins-tokens//. (Erişim Tarihi: 01/08/2021)
• Türkiye Cumhuriyet Merkez Bankası [TCMB], (2018), “Kâğıt Paranın Tarihçesi”, https://www.tcmb.gov.tr/wps/wcm/connect/d189b219-fe71-40bf-9754-6a5f7d0a65eb/KagitParaTarihce.pdf?MOD=AJPERES&CVID=. (Erişim Tarihi: 21/06/2021)
• Toda, H. Y., ve Yamamoto, T., (1995), “Statistical Inference in Vector Autoregressions with Possibly Integrated Processes”, Journal of Econometrics, 66(1-2): 225-250.
• ScrapeHero, Web Scraping Services based in the USA, (2018), https://www.scrapehero.com/. (Erişim Tarihi: 30/04/2021).
• Witten, I.H., (2005), “Text Mining”, Practical Handbook of Intenet Computing”, 14(1): 1-23.
• Yen, K. ve Cheng, H., (2021), “Economic Policy Uncertainty and Cryptocurrency Volatility”, Financial Researh Letters, 38(101428).
• Zhang, X., Fuehres, H., ve Gloor, P. A,. (2012), “Predicting Asset Value through Twitter Buzz”, Advances in Intelligent and Soft Computing, 113: 23-34.